Method and system for heterogeneous event detection

Abstract

A method and system for heterogeneous event detection. Sensor data is obtained and divided into discrete data windows. Each data window is defined by and corresponds to a time period of the sensor data. A time-frequency representation over the time period is calculated for each data window. A filter mask is calculated based on the data window corresponding to the time-frequency representation. The filter mask is applied for reverting the time-frequency representation to a time representation, resulting in filtered data. Features, such as extrema or other inflection points, are identified in the filtered data. The features define events, and transforming the time-frequency representation back into the time domain emphasizes differences between more and less prominent frequencies, facilitating identification of heterogeneous events. The method and system may be applied to body movements of people or animals, automaton movement, audio signals, light intensity, or any suitable time-dependent variable.

We claim: 
     
         1 . A system for determining a biometric, comprising:
 a wearable device comprising a sensor for receiving a pressure stimulus and generating pressure data; and   a processor in communication with the sensor for receiving the pressure data from the sensor, wherein the processor is configured to define a data window over a time period of the pressure data, calculate a time-frequency representation of the data window, calculate a filter mask based on the time-frequency representation, filter the time-frequency representation with the filter mask to provide filtered data, identify features in the filtered data, and determine the biometric from the features in the filtered data.   
     
     
         2 . The system of  claim 1 , wherein the filter mask comprises non-binary values proportional to a positive exponent of a magnitude of a time-frequency transform, and wherein more prominent frequencies are emphasized, and less prominent frequencies are de-emphasized. 
     
     
         3 . The system of  claim 1 , wherein the processor is further configured to generate feedback for the user based on the biometric. 
     
     
         4 . The system of  claim 3 , wherein the biometric comprises a rate of pronation or a rate of supination. 
     
     
         5 . The system of  claim 3 , wherein the biometric comprises a foot strike zone, and wherein the processor is further configured to determine the foot strike zone from a foot strike analysis. 
     
     
         6 . The system of  claim 5 , wherein the feedback comprises a suggestion to move the foot strike zone to another foot location. 
     
     
         7 . The system of  claim 3 , wherein the biometric comprises a fall probability. 
     
     
         8 . The system of  claim 3 , wherein the feedback comprises a suggestion to minimize a risk of injury and/or to improve a gait efficiency. 
     
     
         9 . The system of  claim 3 , wherein the processor is further configured to generate the feedback as at least one of a visual, audio, or tactile alert. 
     
     
         10 . The system of  claim 1 , wherein the processor is further configured to modify a system function of the wearable device based on the biometric to minimize a risk of injury or to improve a gait efficiency. 
     
     
         11 . The system of  claim 10 , wherein the processor is configured to select a system function, wherein the system function comprises at least one of a bladder inflation, a material stiffness, and an output of the wearable device. 
     
     
         12 . The system of  claim 1 , wherein the pressure data is associated with a repetitive body movement of the user, and the repetitive body movement comprises at least one of running, walking, and jumping. 
     
     
         13 . A method for determining a biometric, comprising:
 receiving pressure data from a sensor in a wearable device;   defining a data window over a time period of the pressure data;   calculating a time-frequency representation of the data window;   calculating a filter mask based on the time-frequency representation;   filtering the time-frequency representation with the filter mask to provide filtered data;   identifying features in the filtered data; and   determining a biometric from the features in the filtered data.   
     
     
         14 . The method of  claim 13 , wherein the filter mask comprises non-binary values proportional to a positive exponent of a magnitude of a time-frequency transform, and wherein more prominent frequencies are emphasized, and less prominent frequencies are de-emphasized. 
     
     
         15 . The method of  claim 13 , further comprising generating feedback for the user based on the biometric. 
     
     
         16 . The method of  claim 15 , wherein the biometric comprises a rate of pronation or a rate of supination. 
     
     
         17 . The method of  claim 15 , wherein the biometric comprises a foot strike zone, and the foot strike zone is determined from a foot strike analysis. 
     
     
         18 . The method of  claim 17 , wherein the feedback comprises a suggestion to move the foot strike zone to another foot location. 
     
     
         19 . The method of  claim 15 , wherein the biometric comprises a fall probability. 
     
     
         20 . The method of  claim 15  wherein the feedback comprises a suggestion to minimize a risk of injury and/or to improve a gait efficiency.